Work

lsh-telematic

Experience footageThe concept for this project was a multiplayer game of jumprope within the browser. The idea was that each player has their own role (jumper, swinger).

In its original concept, the goal was to have the experience be a one-to-two person connection, where two people swing the rope while the third jumps. Due to the limitations of trying to get the physics to work across browsers, the scope has been limited to one-to-one person connections in synchrony. The complementary roles of jumper and swinger would need to be fleshed out if I was to continue working on this sketch. There is a certain power dynamic between being the one swinging the rope and the one jumping. Participants are anonymous, but anonymity does not have a significant impact on the experience. Location is also less important, though due to timing, being in the same room probably makes the experience easier to manage. The project is ultimately trying to explore a novel interaction over wireless connections in browser. Unfortunately, the project is unfinished currently as the logic turned out to be difficult to crack. In order to solve the physics issues, I have the rope swinger using real physics, while the jumper just has points mirroring the swinger. If I were to take this further, I would implement a reward/interaction system for the jump interaction.

sovid – ML Toe Dipping

edges2cats

I found it interesting to see how the algorithm distinguished a nose from an eye, especially in sketches that weren't trying to resemble a cat.

GanPaint 

original:

new:

ArtBreeder

and ocean in the field

french horn funghi

I found this really useful for character design in the portrait mode - you could create a whole family of people that were clearly related from one photo.

Infinite Patterns

original:

new:

TalkToTransformer

GoogleAI

I played around with the "How New Yorker are You" experiment, in which two players compete to be crowned the realest New Yorker by answering questions based on tweets that originated in NYC from the past year.  The closer your responses are to the topic--and the faster you respond--the higher you score.

ilovit – MLtoedipping

Pix2Pix

I tried to make a dog cat.

It's interesting how tiny gestures can greatly affect the certainty of the resulting image, and what it interprets as negative or positive space. I tried pretty hard to get it to interpret lines as certain things

GANPaint

It took me a little while to figure out that the painting here can only really alter an already existing element so that it becomes something else, and not really create new elements in most cases.  It's also interesting how the generated fields always seem more flat than the original image.

ArtBreeder

General:

Portraits:

The set of portraits to crossbreed with are almost all really attractive people. It is kinda hard to make a portrait without beautiful eyes. The genetic metaphor is apt - you can almost guess what parts of each image are the result of what "ancestor."

Infinite Patterns by Alexander Mordvintsev

GPT-2

Eight years ago, when I was studying to convert but hadn't yet been to the mikveh, I experienced Simchat Torah for the first time. I had successfully 《reconciled​ to God. That's all the conversion I have to tell. I was on Shabbat observing the service with an older Jewish friend and he mentioned that he would be joining us the next day. When I entered the service, I sat in the front row as the rabbi took our seats. As he began his service, I saw him and, after a moment, I was shocked. Instead of holding the Torah over his head and repeating the name of the Lord, as a Hasid or Rabbi would do, he placed it in front of him over his right hip and the congregation began to pray. I looked at him. I thought to myself, This is a Hasidic man. What is he doing. I didn't know how to respond because it was completely unfamiliar. I said to myself that I just wasn't prepared to be a Hasid, to be surrounded by Orthodox people, to have a large group

"No, Shirley!" I cried as she began to climb over the bed and then started into the chair again.

"If it is too much trouble don't say anything," she said, still sounding like Shirley.

"I may not want to," I promised, "but I can't help it, can I?"

"Yes," she said, and I was quite sure she sounded disappointed.

Sitting there, staring at the empty window and the uninviting sunlight, Shirley sighed.

"Why, why, it's so nice out here!" she protested. "This is our house, after all, and our people, our house! I don't know what to do any more! I feel so empty like this."

"No," I insisted. "This is not our house... it's not my house."

"Oh, of course it is!" she cried. "You don't know what it means to stay on good ground. You have to! But it's time you did."

Google AI Experiments

It rarely correctly guesses what you're drawing. You start to notice after a little while what the typical graphical representation of the thing being drawn seems to be. Sometimes it's not the image I have in my head of the thing.

https://magenta.tensorflow.org/assets/sketch_rnn_demo/index.html

meh – ML Toe Dipping

Edges 2 Cats

(cat paw!)

Using cat to create a rat actually looks more like rat than cat!

Facades

GANPaint Studio

 

This would be so cool if using in CGI or special effect to morph one place into another.

Art Breeders

General:

I am lowkey disgusted by teddy beetles but also I kind of see the little traces of cuteness. I wish I can teddify all the beetles in the world and the world would be so much better.

Portrait:

Infinite Patterns

GPT-2

Google AI Experiments

NSynth: Sound Maker by Yotam Mann

vikz-ML

A. Pix2Pix

edges2cats

For edges2cats, I found it most fun and interesting when I would try to create things completely unlike cats -- for example, a teacup, and see what kind of "cat" would be created. I found it odd, however, that when I did strive to make a cat, it didn't seem to register it all that well (ie. my double headed cats)

facades 

Facades was also interesting to play with in that it allowed me to create this unique entities that, in my opinion, are barely recognizable as buildings and architecture.

B. GANPaint Studio

GANPaint studio, in my experience, was a bit more frustrating to use. I had some difficulty in painting over certain areas and altering the landscape. The "dome feature" was the only one that I could paint over in random areas and have be the most notably.

C. ArtBreeder

General 

Portrait 

The most intriguing part of ArtBreeder for my was by far toggling between the different percentage of genes in each photo. Even merely scaling one gene on one side of the spectrum to the other side of the spectrum produced crazy diverse results. I found it interesting how I managed to create something that looks of a bread / boiled crab / cheesey tomato dish without using a single element of anything of that sort.

D. Infinite Patterns by Alexander Mordvintsev

Original Image

 

Tiling Image

E. GPT-2

How to make a chicken pot pie in under 5 minutes:  This recipe makes over 8 chicken pot pie, or 6 for a larger meal.  Make sure your soup is very soupy and thick before pouring your soup into a pie shell.  This chicken pot pie is also great with a crust or rice pudding.  

3 lbs bone in chicken, skin on for quick cooking for lunch/dinner  

3 cups chicken stock (or broth)

1/2 tsp salt

1/2 tsp pepper

1/2 tsp garlic powder

1/2 cup onions, chopped

12 eggs, whisked and peeled

1 egg white, whisked

a splash of lemon juice

1 Tbsp olive oil

1 1/2 cups baby carrots, peeled and chopped

1 tsp vanilla extract

1 cup chicken stock (or broth) 

a dash of red wine vinegar

2 tsp salt

1 egg, beaten with about 1/3 cup of the stock (or broth) in a small bowl (preferably more than your own cooking water)

2 Tbsp extra virgin olive oil

It all started when I first met her at 【Lion King